© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 0-RES-JB
    11. 6418
    Prev
    Next
    INDEX
    Explanations

    references to different bodies of water

    oai_token-act-pair · gpt-3.5-turbo

    references to water bodies or bodies of water in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ign
    -0.67
    HD
    -0.66
    eat
    -0.65
    Cent
    -0.62
    frame
    -0.62
    Num
    -0.61
     Annie
    -0.61
     Passive
    -0.60
    die
    -0.60
    kick
    -0.59
    POSITIVE LOGITS
     waters
    4.02
    waters
    2.38
     waterways
    1.88
     seas
    1.85
     shores
    1.70
     Waters
    1.58
     oceans
    1.56
     reefs
    1.49
    water
    1.47
     skies
    1.43
    Activations Density 0.018%

    No Known Activations